MIT AI Risk Repository · domain 7: AI system safety, failures, & limitations
7.3 Lack of capability or robustness
AI systems that fail to perform reliably or effectively under varying conditions, exposing them to errors and failures that can have significant consequences, especially in critical applications or areas that require moral reasoning.
Risk entries
126
Frameworks citing it
12
Recorded incidents
305
Incidents since 2020
207
Causal entity (risk entries)
Causal entity (risk entries)
Label
Value
AI
81
Human
22
Other
20
Not coded
3
Intent (risk entries)
Intent (risk entries)
Label
Value
Unintentional
89
Other
28
Intentional
6
Not coded
3
Timing (risk entries)
Timing (risk entries)
Label
Value
Post-deployment
64
Other
32
Pre-deployment
27
Not coded
3
Recorded incidents per yearIncident date; current year partial
Recorded incidents per year
Label
Value
2012
3
2013
3
2014
7
2015
9
2016
16
2017
18
2018
21
2019
14
2020
31
2021
36
2022
31
2023
27
2024
32
2025
37
2026
13
Entries by levelRisk categories, subcategories and additional evidence coded to this subdomain
"Besides behaviors that clearly violate the law, there are also many other activities that are immoral. This category focuses on morally related issues. LLMs should have a high level of ethics and be...
SafetyBench: Evaluating the Safety of Large Language Models with Multiple Choice Questions (Zhang2023) · AI · Other · Post-deployment
